Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images
This addresses the challenge of acquiring pixel-wise annotations for medical image segmentation, offering a domain-specific solution that is incremental by building on existing semi-supervised approaches.
The paper tackles the problem of incomplete object coverage in semi-supervised 3D medical image segmentation by proposing a shape-aware strategy that enforces geometric constraints, resulting in outperforming state-of-the-art methods on the Atrial Segmentation Challenge dataset with improved shape estimation.
Semi-supervised learning has attracted much attention in medical image segmentation due to challenges in acquiring pixel-wise image annotations, which is a crucial step for building high-performance deep learning methods. Most existing semi-supervised segmentation approaches either tend to neglect geometric constraint in object segments, leading to incomplete object coverage, or impose strong shape prior that requires extra alignment. In this work, we propose a novel shapeaware semi-supervised segmentation strategy to leverage abundant unlabeled data and to enforce a geometric shape constraint on the segmentation output. To achieve this, we develop a multi-task deep network that jointly predicts semantic segmentation and signed distance map(SDM) of object surfaces. During training, we introduce an adversarial loss between the predicted SDMs of labeled and unlabeled data so that our network is able to capture shape-aware features more effectively. Experiments on the Atrial Segmentation Challenge dataset show that our method outperforms current state-of-the-art approaches with improved shape estimation, which validates its efficacy. Code is available at https://github.com/kleinzcy/SASSnet.